New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Empirical Research Methods

by Citrus-bit in Citrus-bit/Anaxa

A skill your agent uses for empirical social-science research, applied economics, public policy, education, finance, management, sociology, psychology, epidemiology, or public-health data studies.

CC-BY-SA-4.0Auto-check passedResearch & Science

Install Empirical Research Methods

skills CLI
$ npx skills add Citrus-bit/Anaxa --skill empirical-research-methods -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Citrus-bit/Anaxa empirical-research-methods --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Citrus-bit/Anaxa.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/public/empirical-research-methods .claude/skills/empirical-research-methods && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
empirical-research-methods
GitHub stars
120
Token cost
~1.9k tokens
SKILL.md length
789 words
Files
1
Skills in repo
15
Repo updated
First seen
Licence
CC-BY-SA-4.0

At a glance

A skill your agent uses for empirical social-science research, applied economics, public policy, education, finance, management, sociology, psychology, epidemiology, or public-health data studies.

  • Works in 4 steps: Intake And Data Contract → Method Selection → Mandatory Empirical Outputs → …
  • Empirical social-science research
  • SKILL.md covers Use This Skill For, Core Principle, MedrixFlow Routing and Workflow Contract, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Empirical Research Methods is an agent skill from Citrus-bit/Anaxa. Use this skill for empirical social-science research, applied economics, public policy, education, finance, management, sociology, psychology, epidemiology, or public-health data studies. It routes DID, staggered DID, IV, RDD, PSM/IPW, synthetic control, DML, causal forest, panel regression, event studies, target-trial emulation, TMLE, survival analysis, Table 1, robustness checks, heterogeneity, mechanisms, replication packages, and journal-style empirical paper outputs into MedrixFlow's research quest and…

Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Research & Science, covering Econometrics and empirical research. It works with Python. The repository describes itself as: Anaxa 是一个面向科研工作流的开源智能体系统。它不是单纯的聊天机器人，也不是无人监管的自动发论文机器，而是把文献检索、证据审计、实验执行、论文写作、同行评审式检查和最终产物打包放进同一个可追踪的研究生命周期中。 The licence is CC-BY-SA-4.0.

When your agent uses it

  • Empirical social-science research
  • Applied economics
  • Public-health data studies

Example prompts

  • “/empirical-research-methods”

Requirements

  • Python 3

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Intake And Data Contract
  2. Method Selection
  3. Mandatory Empirical Outputs
  4. Identification Gates

What it can do on your machine

Read from SKILL.md and the folder at commit d57c708. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are json).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • github.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Empirical Research Methods loads about 1.9k tokens when it runs. Until then it costs about 141 tokens; SKILL.md has 789 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~141
When it runs · the whole SKILL.md, loaded when a task matches
~1.9k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Citrus-bit/Anaxa at commit d57c708, republished under its CC-BY-SA-4.0 licence (© Citrus-bit). 789 words, ~1,908 tokens.

Download SKILL.mdSave it as .claude/skills/empirical-research-methods/SKILL.md (or your agent's skills folder).
name
empirical-research-methods
description
Use this skill for empirical social-science research, applied economics, public policy, education, finance, management, sociology, psychology, epidemiology, or public-health data studies. It routes DID, staggered DID, IV, RDD, PSM/IPW, synthetic control, DML, causal forest, panel regression, event studies, target-trial emulation, TMLE, survival analysis, Table 1, robustness checks, heterogeneity, mechanisms, replication packages, and journal-style empirical paper outputs into MedrixFlow's research quest and experiment_lab workflows.
license
CC BY-SA 4.0 derivative guidance from Awesome-Agent-Skills-for-Empirical-Research

Empirical Research Methods

This skill adapts the workflow ideas from Awesome Agent Skills for Empirical Research into MedrixFlow. It is a routing and integrity layer, not a vendored copy of the whole upstream repository.

Use This Skill For

  • empirical papers in economics, policy, education, finance, management, sociology, psychology, epidemiology, public health, or related social-science fields
  • causal inference or econometric analysis: DID, staggered DID, IV, RDD, PSM/IPW, entropy balancing, synthetic control, DML, causal forest, target-trial emulation, TMLE, survival, mediation, heterogeneity, mechanisms
  • requests such as "run a full empirical analysis", "make Table 1", "event study", "parallel trends", "robustness checks", "replication package", "AER/QJE style table", or "Quarto/Stata/R/Python empirical workflow"
  • automatic research quests whose experiment stage depends on a real dataset and a defensible identification strategy

Core Principle

Treat empirical work as a staged design argument, not a single model fit. The agent must first establish the data contract and estimand, then run diagnostics, then estimate, then stress-test, then package results for review.

MedrixFlow Routing

  • Use research_assistant when the user wants a staged automatic research project, manuscript lifecycle, human gates, reviewer loop, or final bundle.
  • Use academic_research only for related work, identification precedent, measurement precedent, and citation grounding.
  • Use experiment_lab for execution on local data. Pass method information in analysis_type and metadata, including the chosen empirical method, estimand, identifiers, time variables, treatment variables, covariates, fixed effects, cluster level, and robustness plan.
  • Use manuscript_export only after empirical claims have corresponding result artifacts and citation evidence.

Workflow Contract

1. Intake And Data Contract

Before estimation, identify:

  • outcome variable
  • treatment or exposure variable
  • unit identifier and time variable for panel/event-study designs
  • treatment timing for DID/staggered DID
  • running variable and cutoff for RDD
  • instrument for IV
  • matching/IPW covariates for PSM/IPW
  • cluster level and fixed effects
  • sample restrictions and missing-data policy
  • primary estimand: ATE, ATT, LATE, CATE, event-time effect, risk difference, hazard ratio, or predictive metric

If these are missing and cannot be inferred from uploaded data, ask for them or create a blocked research quest entry. Do not silently choose a causal design.

2. Method Selection

Use this decision table:

User/Data SignalDefault Route
panel policy timing, treated/control groupsDID or staggered DID
staggered adoption or heterogeneous timingmodern staggered DID; avoid plain TWFE as the only result
plausible discontinuity thresholdRDD with bandwidth, density, and covariate balance checks
endogenous treatment plus instrumentIV/2SLS with first-stage F and overidentification checks when applicable
selection on observablesPSM/IPW/entropy balancing plus balance diagnostics
single treated unit or few treated unitssynthetic control or synthetic DID
high-dimensional nuisance controlsDML/causal forest with cross-fitting and CATE diagnostics
public-health cohort or RWE requesttarget-trial emulation, IPTW/g-formula/TMLE, survival where applicable
no treatment or causal estimanddescriptive, predictive, or correlational analysis only; label it accordingly
Show full SKILL.md (340 more words)Show less
3. Mandatory Empirical Outputs

For a full empirical analysis, produce an artifact bundle with:

  • experiment_plan.md: research question, estimand, identification assumptions, variables, sample restrictions, budget, and human approvals
  • methods.md: data cleaning, model equations, fixed effects, standard errors, diagnostics, and limitations
  • results.md: main findings with cautious interpretation
  • metrics.json: structured estimates, standard errors, p-values, fit metrics, diagnostics, and robustness status where available
  • figure_manifest.json
  • tables: Table 1 / balance, main results, robustness, heterogeneity, and mechanisms when applicable
  • figures: trend/event-study/RD/balance/coef/spec-curve plots when applicable
  • reproducibility_ledger.json or equivalent metadata recording dataset paths, seeds, package fallbacks, and skipped checks
4. Identification Gates

Block or downgrade causal language when:

  • treatment assignment is not plausibly exogenous and no design handles it
  • DID lacks a credible pre-trend or event-study check when pre-period data exists
  • IV has weak first-stage evidence
  • RDD lacks density/covariate-balance diagnostics
  • PSM/IPW lacks post-adjustment balance diagnostics
  • DML/CATE work lacks cross-fitting or honest sample splitting where relevant
  • the dataset has no declared outcome/treatment for causal claims

When blocked, preserve the exploratory outputs and state what design input is missing. Do not turn correlation into causation.

Experiment Lab Metadata Pattern

When calling experiment_lab, include metadata like:

json
{
  "skill": "empirical-research-methods",
  "empirical_method": "did",
  "estimand": "ATT",
  "outcome": "y",
  "treatment": "treated",
  "unit_id": "unit_id",
  "time": "year",
  "treatment_time": "first_treat_year",
  "covariates": ["x1", "x2"],
  "fixed_effects": ["unit_id", "year"],
  "cluster": "unit_id",
  "required_outputs": ["table1", "main_results", "event_study", "robustness"]
}

Use analysis_type values such as did, staggered_did, iv, rdd, psm, synthetic_control, dml, causal_forest, target_trial, tmle, survival, regression, or classification. If the current backend does not implement the requested estimator, run the closest safe descriptive or regression workflow, mark the requested method as not executed, and keep the quest blocked before causal manuscript claims.

Writing Rules

  • Separate literature evidence from empirical evidence.
  • Cite method precedent through academic_research; cite actual estimates only from generated artifacts.
  • Use cautious language: "associated with" for non-causal designs; "estimated effect" only when the identification gate passes.
  • For paper outputs, feed the empirical result artifacts and claim map into manuscript_export; do not write unsupported causal claims.

Source Basis

This skill takes the useful structure from the upstream Awesome Agent Skills for Empirical Research project: StatsPAI-style agent-native causal workflows, classical Python/R/Stata 8-step empirical pipelines, method-specific checks (DID/IV/RDD/PSM/SCM/DML), and reproducibility packaging. It intentionally avoids blindly importing huge third-party skill bundles or assuming proprietary tools are installed.

© Citrus-bit, CC-BY-SA-4.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/public/empirical-research-methods of Citrus-bit/Anaxa.

Open the folder on GitHubat commit d57c708

Compare with similar skills

Empirical Research Methods next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Empirical Research Methods compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Empirical Research Methods this skillCitrus-bit/Anaxa120—~1.9kAutomated safety check: PassCC-BY-SA-4.0
Stata C Pluginsdylantmoore/stata-skill2911 repos~5.8kAutomated safety check: PassCustom licence
Capture Environmentpedrohcgs/claude-code-my-workflow1.7k—~2.8kAutomated safety check: NotesMIT
Fin Data Acquisitioncsmar432/finai-research109—~2kAutomated safety check: PassMIT
Diagnosepedrohcgs/claude-code-my-workflow1.7k—~4.2kAutomated safety check: PassMIT
Differential Auditpedrohcgs/claude-code-my-workflow1.7k—~1.6kAutomated safety check: NotesMIT

Similar skills

  • Stata C Plugins

    dylantmoore/stata-skill

    Develop high-performance C/C++ plugins for Stata using the stplugin.h SDK.

    291 GitHub starsUsed in 1 repo~5.8k tokens
    Research & ScienceAuto-check passed

  • Capture Environment

    pedrohcgs/claude-code-my-workflow

    Snapshot the computational environment for a replication package — detects the analysis stack (R / Stata / Python) and emits the right lockfiles (renv.lock + sessionInfo.txt, requirements.txt /…

    1.7k GitHub stars~2.8k tokensUpdated 12 days ago
    Research & ScienceAuto-check: notes

  • Fin Data Acquisition

    csmar432/finai-research

    根据REFINEDDESIGN.md中的变量定义，自动获取所需数据并生成可执行的回归分析脚本（Python/Stata）。

    109 GitHub stars~2k tokensUpdated 4 days ago
    Research & ScienceAuto-check passed

  • Diagnose

    pedrohcgs/claude-code-my-workflow

    Root-cause a failing or wrong empirical result with a disciplined reproduce → minimise → hypothesise → instrument → fix loop, instead of guessing-and-poking.

    1.7k GitHub stars~4.2k tokensUpdated 12 days ago
    Research & ScienceAuto-check passed

  • Differential Audit

    pedrohcgs/claude-code-my-workflow

    Compare two implementations of the same thing — a port (R↔Python↔Stata), a reimplementation, a replication package, a refactor, or a new version against the old — so that agreement means something.

    1.7k GitHub stars~1.6k tokensUpdated 12 days ago
    Research & ScienceAuto-check: notes

  • Audit Reproducibility

    pedrohcgs/claude-code-my-workflow

    Enforce the replication-protocol.md rule by cross-checking numeric claims in a manuscript against the actual R / Stata / Python outputs.

    1.7k GitHub stars~6.4k tokensUpdated 12 days ago
    Research & ScienceAuto-check: notes

More from Citrus-bit/Anaxa

All 15 skills in this repo

  • Nature Figure

    Citrus-bit/Anaxa

    Submission-grade Nature/high-impact journal figure workflow for Python or R.

    120 GitHub starsUsed in 2 repos~2.7k tokens
    Auto-check passed

  • Chart Visualization

    Citrus-bit/Anaxa

    A skill your agent uses whenever the user wants a chart, graph, plot, dashboard visual, or asks to visualize structured numbers, trends, comparisons, proportions, distributions, correlations…

    120 GitHub stars~2.4k tokensUpdated 1 mo ago
    Auto-check passed

  • Claude To Medrixflow

    Citrus-bit/Anaxa

    Interact with MedrixFlow AI agent platform via its HTTP API.

    120 GitHub stars~1.7k tokensUpdated 1 mo ago
    Auto-check passed

  • Fireworks Tech Graph

    Citrus-bit/Anaxa

    A skill your agent uses when the user wants to create any technical diagram - architecture, data flow, flowchart, sequence, agent/memory, or concept map - and export as SVG+PNG.

    120 GitHub stars~5.4k tokensUpdated 1 mo ago
    Auto-check passed

  • Bootstrap

    Citrus-bit/Anaxa

    Generate a personalized SOUL.md through a warm, adaptive onboarding conversation.

    120 GitHub stars~1.2k tokensUpdated 1 mo ago
    Auto-check passed

  • Deep Research

    Citrus-bit/Anaxa

    A skill your agent uses for general web research that needs current online information, multiple source angles, and synthesis, when no more specific research skill applies.

    120 GitHub stars~1.9k tokensUpdated 1 mo ago
    Auto-check passed

Works with

Categories

Questions about Empirical Research Methods

What does Empirical Research Methods do?

A skill your agent uses for empirical social-science research, applied economics, public policy, education, finance, management, sociology, psychology, epidemiology, or public-health data studies. Empirical Research Methods is an agent skill from Citrus-bit/Anaxa. Use this skill for empirical social-science research, applied economics, public policy, education, finance, management, sociology, psychology, epidemiology, or public-health data studies.

When should I use Empirical Research Methods?

Empirical Research Methods fits situations like: empirical social-science research; applied economics; public-health data studies.

How do I install Empirical Research Methods in Claude Code?

Run `npx skills add Citrus-bit/Anaxa --skill empirical-research-methods -a claude-code`. Or copy the skill folder (skills/public/empirical-research-methods in Citrus-bit/Anaxa) into .claude/skills/empirical-research-methods in your project. Claude Code loads it when a task matches its description.

How do I install Empirical Research Methods in Codex?

Run `npx skills add Citrus-bit/Anaxa --skill empirical-research-methods -a codex`. Or copy the skill folder (skills/public/empirical-research-methods in Citrus-bit/Anaxa) into .agents/skills/empirical-research-methods in your project. Codex loads it when a task matches its description.

Can I use Empirical Research Methods in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Citrus-bit/Anaxa --skill empirical-research-methods -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/empirical-research-methods, .gemini/skills/empirical-research-methods, .github/skills/empirical-research-methods and .opencode/skills/empirical-research-methods in your project.

What does Empirical Research Methods need to run?

SKILL.md names no scripts, command-line tools or credentials: Empirical Research Methods is instructions for the agent only. Our summary lists: Python 3.

Does Empirical Research Methods access the network?

SKILL.md names 1 domain. As links in the text: github.com. This is read from the text; nothing was executed.

Is Empirical Research Methods safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Empirical Research Methods use?

Empirical Research Methods is published under the CC-BY-SA-4.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Empirical Research Methods use?

About 1.9k tokens (SKILL.md is roughly 7.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Empirical Research Methods?

Skills that share tags, products or a category with Empirical Research Methods: Stata C Plugins (dylantmoore/stata-skill, 291 stars), Capture Environment (pedrohcgs/claude-code-my-workflow, 1.7k stars), Fin Data Acquisition (csmar432/finai-research, 109 stars) and Diagnose (pedrohcgs/claude-code-my-workflow, 1.7k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Empirical Research Methods?

Citrus-bit (a GitHub user) maintains it in Citrus-bit/Anaxa, which has 120 GitHub stars. The repository holds 15 skills in this directory. The repository was last updated on September 7, 2026.

Source: Citrus-bit/Anaxa on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.